Back to search results
Qwen3.5-4B · IQ2_M
Apple M5 Max128GBvLLM v0.44L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-4B (IQ2_M) on Apple M5 Max with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
364.07 tok/s
Decode
Decode speed
1,250.03 tok/s
Prefill
Prefill speed
1.3 s
TTFT
Time to first token
6.47 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- llama.cpp · IQ3_S Decode 279.98 · Prefill 1354 ·
- Strata · Q3_K_L Decode 354.31 · Prefill 1310.91 ·
- Strata · Q5_K_S Decode 279.1 · Prefill 1192.93 ·
- vLLM · IQ2_M (current)Decode 364.07 · Prefill 1250.03 ·
- vLLM · Q4_K_S Decode 256.46 · Prefill 848.78 ·
- Strata · Q5_K_M Decode 272.64 · Prefill 963.9 ·
Core figures
- Decode (avg)
- 364.07 tok/s
- Prefill (avg)
- 1,250.03 tok/s
- TTFT (avg)
- 1.3 s
- VRAM (avg)
- 6.47 GB
- MTP acceptance rate
- —
- TTFB
- 2.91 GB
- Power draw
- 142 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-4B
- Quantization
- IQ2_M
- Framework
- vLLM
- Version
- v0.44
- Context length
- 8192 tokens
- Batch size
- 16
- GPU layers
- 999
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M5 Max
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 6.47 GB
- OS
- macOS 15.0
- Driver
- Apple M5 Max
- CUDA
- N/A
- Power draw
- 142 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.44 · macOS 15.0 · CUDA N/A · 8192 ctx
364.07 tok/s
Decode
1,250.03 tok/s
Prefill
1.3 s
TTFT
6.47 GB
VRAM
—
MTP
142 W
Power draw
L2 batch seed 2026-10-13: vLLM on hw_id=28 running model_id=48 at IQ2_M